© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38476
    Prev
    Next
    INDEX
    Explanations

    words from Indian context and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     if
    -1.95
    '
    -1.81
     but
    -1.80
     bahwa
    -1.73
     tą
    -1.63
     siguiendo
    -1.63
    恫
    -1.63
    你去
    -1.62
     semua
    -1.59
    たちが
    -1.59
    POSITIVE LOGITS
    </sup>
    2.59
     ytterligare
    2.14
     snabbt
    2.11
     säkert
    2.09
     イラストレーション
    2.06
     godk
    2.05
     läsa
    2.05
     jätte
    2.03
     priser
    2.02
     ganska
    2.00
    Activations Density 0.014%

    No Known Activations